A Survey and Taxonomy of Loss Functions in Machine Learning
AI · 01.04.2026 · 7 (4) · 128
DOI: 10.3390/ai7040128 ↗Kurz gefasst
Fachartikel in der Zeitschrift AI, online erschienen am 01.04.2026. Verfasst von Lorenzo Ciampiconi und 4 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 204 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Most state-of-the-art machine learning techniques revolve around the optimization of loss functions, making the choice of an objective critical to model performance and reliability. Although recent reviews discuss loss functions in specific domains or in deep learning settings, there is still no single reference that presents widely used losses across major task families within a unified formal setting and with consistent optimization-relevant property annotations. In this survey, we compile and systematize the most widely adopted loss functions for regression, classification, generative modeling, ranking, energy-based modeling, and relational learning. Our selection procedure combines seeding from foundational textbooks and prior surveys with cross-checking of highly cited literature and common implementations in mainstream machine learning frameworks. We introduce 52 loss functions and organize them into an intuitive taxonomy, summarizing their theoretical motivation, key mathematical properties, and typical application contexts, with compact appendix tables for quick lookup. This survey is intended as a resource for undergraduate, graduate, and Ph.D. students, as well as researchers seeking a structured reference for selecting and comparing loss functions.
Zitieren
APA
Ciampiconi, L., Elwood, A., Leonardi, M., Mohamed, A., & Rozza, A. (2026). A Survey and Taxonomy of Loss Functions in Machine Learning. AI, 7(4), 128. https://doi.org/10.3390/ai7040128
Vancouver
Ciampiconi L, Elwood A, Leonardi M, Mohamed A, Rozza A. A Survey and Taxonomy of Loss Functions in Machine Learning. AI. 2026;7(4):128. doi:10.3390/ai7040128
BibTeX
@article{Ciampiconi2026,
author = {Ciampiconi, Lorenzo and Elwood, Adam and Leonardi, Marco and Mohamed, Ashraf and Rozza, Alessandro},
title = {A Survey and Taxonomy of Loss Functions in Machine Learning},
journal = {AI},
year = {2026},
volume = {7},
number = {4},
pages = {128},
doi = {10.3390/ai7040128}
}
EUVIMED